Computer Vision - Udacity
Computer Vision - Udacity
Lession 1: Introduction
Lession 2: Images as functions
1. For Black and White
2. For Color
3. Example Code
4. Class
Sample and Quantize
Image Size
Crop
Color planes
Add two images
Multiply by a scalar
Common Types of Noise
Generate Gaussian Noise
Effect of Sigma on Gauusian Noise
Displaying Images in Matlab
Lesson 3: Filtering
Moving Average in 2D
Correlation filtering
Averaging Filter
Gaussian Filter
Variance or Standard Deviation
Keeping the Two Gaussians Straight
Lesson 4: Linearity and convolution
Intro
Impulse Function and Response
Correlation vs Convolution
Property of Convolution
Computational Complexity and Separability
Boundary Issues
Practicing With Linear Filters
Median Filter
Lesson 5: Filters as templates
Template Matching
Lesson 6: Edge detection: Gradients
Edges
Edge Detection
Derivatives and Edges
What is a Gradient
Finite Differences
Partial Derivatives of an Image
The Discrete Gradient
Sobel Operator
Well Known Gradients
But in the Real World
Lesson 7: Edge detection: 2D operators
Derivative of Gaussian Filter 2D
Canny Edge Operator
Canny Edge Detector
Single 2D Edge Detection Filter
Edge Demo
Lesson 8: hough transform: Lines
Parametric Model
Line Fitting
Voting
Hough Space
Polar Representation for Lines
Baic Hough Transform Algorithm
Complexity of The Hough Transform
Hough Example
Hough Demo
Extensions
Lesson 9: Hough transform: Circles
Detecting Circles with Hough
Powered by
GitBook
Line Fitting
Line Fitting
Difficulty of line fitting
Extra edge points(cluter), multiple models.
Only some parts of each line detected, and some parts are missing.
Noise in measured edge points, orientations
results matching "
"
No results matching "
"